Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/generous-corp/pulp/kitgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/generous-corp/pulp/kit)<a href="https://agentmods.dev/commands/generous-corp/pulp/kit"><img src="https://agentmods.dev/badge/commands/generous-corp/pulp/kit.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00814 |
| Opus 5 | $0.00000 | $0.00407 |
| Sonnet 5 | $0.00000 | $0.00163 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
kit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/kit
Search, inspect, plan, approve, and apply local Pulp kit manifests or .pulpkit archives.
Use this for Pulp-native source, UI, template, validation, graph, and native-component artifacts that should be reviewed before project mutation.
Why it matters:
- developers can share real Pulp building blocks instead of copy-pasted examples;
- users see capabilities, licenses, files, and project changes before approval;
- agents can inspect and plan without running untrusted package code.
Keep curated dependency packages on pulp add <name>. Use pulp kit when the artifact may transform project structure, install files, or introduce executable source. .pulpkit archives must include files.sha256.json; every payload file must be listed there and hashes must match before validation, planning, verification, apply, or publish dry-run.
Common commands:
pulp kit validate <path>
pulp kit search <query> --root <dir> --lane kit --json
pulp kit search <query> --root <dir> --lane content --json
pulp kit validate <path> --json
pulp kit inspect <path> --json
pulp kit plan <path> --project <dir> --json
pulp kit verify <path> --project <dir> --json
pulp kit verify <path> --project <dir> --execute-screenshots --json
pulp kit apply <path> --project <dir> --yes
pulp kit remove <kit-id> --project <dir> --yes
pulp kit pack <path> --output <file> --json
pulp kit publish <path> --dry-run --json
pulp kit publish <path> --dry-run --registry-manifest <file> --json
pulp kit init --kind source --id com.example.my-kit --dir ./my-kit
Workflow:
- Validate or inspect the manifest.
- Plan to preview project changes.
- Verify declared validation profiles after reviewing the plan.
- Apply only after explicit approval.
- Remove only from constrained lock-recorded kit ownership.
Trust rules:
- metadata commands never run package CMake, JavaScript, scripts, dynamic libraries, remote search, or content installers;
- archives must include
files.sha256.json, and every payload file must be listed and hash-matched before the manifest is trusted; - validation checks manifest shape, licenses, Pulp/C++ requirements, known Pulp module dependencies, and declared evidence hashes before plan/apply;
content-packmanifests can be searched, validated, and inspected, butpulp kit plan/apply/publishrejects them; usepulp content ...;- apply writes only owned files and records the reviewed manifest digest in
.pulp/kits.lock.json; - remove deletes only constrained lock-recorded kit paths under
pulp-kits/<kit-id>/...plus known generated lock/CMake files.
Prefer structured authoring provenance. authoring.createdBy.type should be human, agent, or mixed; agent-created packages are not publish-ready until authoring.humanReview.reviewed is true.
Developer notes:
pulp kit searchis local discovery only; it never fetches and never makes a result trusted.- Template kits need
validation.generatedProjectDiffsbeforepulp create --template <kit-dir>. - UI kits need screenshot evidence. Run
pulp kit verifyafter plan review; use--execute-screenshotsonly when rendered artifacts are explicitly needed. - After apply, use
pulp_use_kit_ui(...)only when the developer chooses to attach the reviewed script/tokens/assets. - Graph/native kits must surface exported fixtures/files, platform claims, and realtime claims before apply. Verification must not load dynamic libraries.
- Signed
node-packkits must not claim iOS/AUv3 support.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 61 lines · 0 tokens per session scan A ebe90f88f2af
kit is a command published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 814 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.